Volume 7,Issue 3
Precision Nutrition Supply Models for Laying Hens: Divergence, Integration and Application Advances between Industrial Scaled Farms and Family Holdings
The two main forms of the world's egg industry are large-scale farms (LSFs) equipped with new technologies, and smallholder family farms (FFs) that have limited resources and different management. Precision nutrition has been introduced to the industrial system, but it has not yet been applied in family farms; therefore, this review will systematically compare the supply models of precision nutrition in the two systems across the five areas of calcium-phosphorus homeostasis, gut health modulation, housing environment interaction, energy-to-protein ratio optimisation, and integrative precision nutrition framework, and based on recent data (2021-2026), demonstrate that they are different. To meet the various nutritional requirements of plants in a new way, some new technologies have been introduced for LSF, such as real-time sensing, machine learning and automatic feeding (R² > 0.90). FFs are simple, low-cost decision tools that have only a few factorial coefficients and local additives, and their regulation of calcium and phosphorus is different from that of LSFs; therefore, FFs are used to express strain-specific transporters and vitamin D metabolites. FF is gradually introducing herbal ultrafine powders that have shown some improvement in gut health. Housing corrections are not all the same. Net Energy Systems can lower the feed cost of both types of systems by 3%-8%, but the way to achieve this is different; we will provide comparison tables showing the model architecture, validation results and economic threshold for each. Finally, there have been some convergences in the areas of open-source digital tools, transgenerational programming and the responsible nutrition framework. They can address the accuracy problem and consider the different conditions of different systems.
[1] Zhang L, Xing H, Delgado MS, et al., 2024, A hybrid modelling approach for precision feeding in caged layers: integrating mechanistic nutrient flow and recurrent neural networks. Anim Nutr, 15: 210-223.
[2] Rostagno HS, Albino LFT, Hannas MI, et al., 2021, Brazilian Tables for Poultry and Swine. 4th ed., UFV.
[3] Neethirajan S, Kemp B, 2023, Digital twins in livestock farming: a systematic review. Comput Electron Agric, 209: 107826.
[4] Wang Y, Li J, Zhao F, et al., 2023, Machine learning prediction of digestible amino acid requirements in laying hens using farm data streams. Poult Sci, 102(8): 102789.
[5] Van Emous RA, Mens AJW, Winkel A, 2022, Factorial modeling of energy and protein requirements for modern laying hens under thermoneutral and heat stress conditions. Animal, 16(6): 100535.
[6] Angel R, Kim SW, Li X, 2023, Precision calcium and phosphorus nutrition: opportunities to reduce environmental footprint. J Anim Sci Biotechnol, 14(1): 42.
[7] Shomina N, et al., 2025, Effects of dietary phosphorus and myo-inositol supplementation on NaPi-IIb and TRPV6 protein expression in duodenal apical membranes of laying hens from two strains. Poult Sci, 105(1): 106171.
[8] Garcia-Mejia AR, Sinclair-Black M, Blair LR, et al., 2024, Physiological changes in the regulation of calcium and phosphorus utilization at the onset of egg production in commercial laying hens. Front Physiol, 15: 1465817.
[9] Huang Q, Nielsen BL, Liu Y, 2023, Gradient boosting for estimating calcium and phosphorus requirements in brown layers across different housing systems. Poult Sci, 102(11): 103045.
[10] Koedijk R, 2022, Protein precision: thriving performance and economics in poultry. Poultry World. visited on April 20, 2026, https://www.poultryworld.net/.
[11] Gui J, Kong XF, et al., 2025, Chinese herbal ultrafine powder (CHUP) improves egg quality, meat nutritional value and intestinal barrier function in late phase laying hens. Poult Sci, in press.
[12] Chen S, Zheng C, Dong X, et al., 2025, Online prediction of methionine requirement using artificial neural network and real time body weight in laying hens. Comput Electron Agric, 210: 107903.
[13] Lu XX, Zhang FD, Wang J, et al., 2024, Research progress on differences of production and nutritional requirements between breeding and commercial laying hens. China Poult, 46(1): 56-63.
[14] Liu Z, Sun W, Jia G, 2024, Deep neural network for dynamic lysine requirement modelling in Hy-Line layers: field validation. J Anim Sci, 102: skae045.
[15] Van der Peet-Schwering CMC, Verdoes N, Ogink NWM, 2023, Environmental effects of precision feeding in laying hens: a life cycle assessment. J Clean Prod, 385: 135702.
[16] Yan L, Li XC, Liu YX, et al., 2025, Effects of net energy system on performance, serum indices and intestinal development of laying hens. Chin J Anim Sci, 61(7): 313-319.
[17] Pan MH, Li BH, Ban ZB, et al., 2025, Comparative study on net energy values of corn and soybean meal in laying hen diets. Chin J Anim Nutr, 37(4): 2210-2220.
[18] Proszkowiec-Wegla M, et al., 2025, ASAS-NANP Symposium: Mathematical modeling in animal nutrition: overview of poultry nutrition modeling. J Anim Sci, 103: skae078.
[19] Moss AF, Chrystal PV, Crowley TM, et al., 2024, Implementation of precision feeding in commercial layers: meta analysis of 15 flock trials. Anim Feed Sci Technol, 308: 115882.
[20] Zhou L, Zhang J, Tang C, 2024, Industrialisation challenges and countermeasures for ω-3 biofortification technology in livestock products. J Agric Sci Technol, 26(5): 1-10.
[21] Van Emous RA, 2025, From precision to responsible layer diets. WATT Poultry. visited on April 20, 2026, https://www.wattagnet.com/.
